Close Menu
TechBrunchTechBrunch
  • Home
  • AI
  • Apps
  • Crypto
  • Security
  • Startups
  • TechCrunch
  • Venture

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

What's Hot

Google suggests opening a play store for more real money games in India

July 30, 2025

Palo Alto Networks agrees to buy Cyberark for $25 billion

July 30, 2025

Germ brings end-to-end encrypted messages to BlueSky

July 30, 2025
Facebook X (Twitter) Instagram
TechBrunchTechBrunch
  • Home
  • AI

    OpenAI seeks to extend human lifespans with the help of longevity startups

    January 17, 2025

    Farewell to the $200 million woolly mammoth and TikTok

    January 17, 2025

    Nord Security founder launches Nexos.ai to help enterprises move AI projects from pilot to production

    January 17, 2025

    Data proves it remains difficult for startups to raise capital, even though VCs invested $75 billion in the fourth quarter

    January 16, 2025

    Apple suspends AI notification summaries for news after generating false alerts

    January 16, 2025
  • Apps

    Google suggests opening a play store for more real money games in India

    July 30, 2025

    Germ brings end-to-end encrypted messages to BlueSky

    July 30, 2025

    A guide to using editing, a cap cut rival for short video editing in meta

    July 30, 2025

    The genai app doubled revenue and grew to 1.7b downloads in the first half of 2025

    July 30, 2025

    Tiktoc's crowdsourcing fact check footnotes will be released in the US

    July 30, 2025
  • Crypto

    Telegram's Crypto Wallet will be released in the US

    July 22, 2025

    Indian Crypto ExchangeCoindCX confirms $44 million stolen during hack

    July 21, 2025

    North Korean hackers blamed record-breaking spikes in 2025

    July 17, 2025

    Bitcoin surpasses $118K at the second highest high in 24 hours

    July 11, 2025

    Vitalik Buterin reserves for Sam Altman's global project

    June 28, 2025
  • Security

    Palo Alto Networks agrees to buy Cyberark for $25 billion

    July 30, 2025

    Hackers stole Social Security Number during Arians Life Cyber Attack

    July 30, 2025

    Minnesota activates the National Guard as St. Paul's cyber attack disrupts public services

    July 30, 2025

    Skechers make kids shoes with hidden air tag compartments

    July 30, 2025

    Google says the UK government has not requested an encryption backdoor for users' data

    July 29, 2025
  • Startups

    7 days left: Founders and VCs save over $300 on all stage passes

    March 24, 2025

    AI chip startup Furiosaai reportedly rejecting $800 million acquisition offer from Meta

    March 24, 2025

    20 Hottest Open Source Startups of 2024

    March 22, 2025

    Andrill may build a weapons factory in the UK

    March 21, 2025

    Startup Weekly: Wiz bets paid off at M&A Rich Week

    March 21, 2025
  • TechCrunch

    OpenSea takes a long-term view with a focus on UX despite NFT sales remaining low

    February 8, 2024

    AI will save software companies' growth dreams

    February 8, 2024

    B2B and B2C are not about who buys, but how you sell

    February 5, 2024

    It's time for venture capital to break away from fast fashion

    February 3, 2024

    a16z's Chris Dixon believes it's time to focus on blockchain use cases rather than speculation

    February 2, 2024
  • Venture

    How New Jersey Startups Find Inspiring Ways to Cut Copper Costs

    July 30, 2025

    Humanity reportedly approaches a $1700 billion valuation, a potential $5 billion round

    July 29, 2025

    The Greek startup is challenging the defence giant with low-cost autonomous weapons systems

    July 29, 2025

    Go inside: Volunteering in the 2025 destruction

    July 29, 2025

    Do startups still need Silicon Valley? Check out 2025 Surpt

    July 28, 2025
TechBrunchTechBrunch

Largest text-to-speech AI model shows 'new capabilities'

TechBrunchBy TechBrunchFebruary 14, 20245 Mins Read
Facebook Twitter Pinterest Telegram LinkedIn Tumblr WhatsApp Email
Share
Facebook Twitter LinkedIn Pinterest Telegram Email


Amazon researchers have trained the largest text-to-speech model ever. This model claims to exhibit “emergent” properties that improve the ability to speak naturally even in complex sentences. A breakthrough could be just what technology needs to get out of the uncanny valley.

These models are constantly growing and improving, but the researchers specifically hoped to see the kind of jump in power that was observed when language models got beyond a certain size. For unknown reasons, as LLMs grow beyond a certain point, they become more robust and versatile, capable of performing tasks for which they were not trained.

This doesn't mean they're gaining sentience or anything, it's just that their hockey-stick performance on certain conversational AI tasks is beyond a certain point. The team at Amazon AGI (it's no secret what they're aiming for) thought the same thing might happen as text-to-speech models grow. And their research suggests that this is indeed the case.

The new model is called Big Adaptive Streamable TTS with Emergent capabilities, which they have twisted into the abbreviation BASE TTS. The largest version of the model uses 100,000 hours of public domain audio, 90% of which is in English and the rest in German, Dutch, and Spanish.

With 980 million parameters, BASE-large is probably the largest model in this category. For comparison, we also trained 400M and 150M parametric models based on 10,000 and 1,000 hours of audio, respectively. So the idea is that if one of these models exhibits emergent behaviors and another doesn't, we can figure out the extent to which those behaviors start. To appear.

As it turned out, the midsize model represented the leap in capability the team was looking for. Not necessarily in the usual voice quality (which is better reviewed, but only by a few points), but in a set of new capabilities that the team observed and measured. . Here are some examples of tricky texts mentioned within papers:

  • compound noun: The Beckhams decide to rent a quaint country house with a charming stone structure.
  • emotions: “Oh my god! Are we really going to the Maldives? That's unbelievable!” Jenny squealed, bouncing on her toes with unbridled glee.
  • foreign words: “Mr. Henri, a well-known chef, has designed a seven-course meal, each with its own unique flavor.
  • paralinguistics (i.e. non-words that can be read): “Shh, Lucy, shh, don't wake your baby brother,” Tom whispered as he tiptoed across the nursery.
  • punctuation mark: She received a strange email from her brother. “There is an emergency at home. Please call us as soon as possible! Mom and dad are worried… #familyissue.”
  • question: But the question of Brexit remains: after all the trials and tribulations, will ministers be able to find an answer in time?
  • Syntactic complexity:De Moya, who recently won the Lifetime Achievement Award, starred in a movie in 2022 that received mixed reviews but became a huge hit at the box office.

“These sentences can be used to parse garden path sentences, add phrasal stress to lengthy compound nouns, produce emotive or whispered sounds, or use foreign words such as 'qi' or '@'. designed to include difficult tasks such as producing the correct phonemes for punctuation. – None of which BASE TTS is explicitly trained to do,” the authors write.

Such features typically trigger the speech synthesis engine, causing it to mispronounce, skip words, use strange intonation, and make other gaffes. Although the BASE TTS still had its problems, it performed much better than his contemporaries such as the Tortoise and VALL-E.

There are many examples of these difficult texts being spoken very naturally on sites created for new models. Of course, these are chosen by researchers, so they are necessarily cherry-picked, but they are impressive nonetheless. If you don't want to click, see some below.


https://techcrunch.com/wp-content/uploads/2024/02/shh-its-starting.wav

https://techcrunch.com/wp-content/uploads/2024/02/how-french.wav

https://techcrunch.com/wp-content/uploads/2024/02/guiding-moonlight.wav

Since the three BASE TTS models share an architecture, it is clear that the size of the model and the range of its training data are responsible for the model's ability to handle some of the complexities mentioned above. Please note that this is still an experimental model and process and is not a commercial model or anything. Future research should identify inflection points for new capabilities and how to efficiently train and deploy the resulting models.

One thing to note is that this model is, as the name suggests, “streamable.” That is, the entire sentence does not have to be generated at once, but is generated moment by moment at a relatively low bitrate. The team also tried packaging audio metadata, such as emotion and prosody, into a separate low-bandwidth stream that could accompany vanilla audio.

It looks like the text-to-speech model could have a breakout moment in 2024. It's just election time. However, there is no denying the usefulness of this technology, especially when it comes to accessibility. The team said it declined to release the source of the model or other data, citing the risk that malicious parties could misuse the model. However, the cat will eventually come out of the bag.



Source link

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email

Related Posts

OpenAI seeks to extend human lifespans with the help of longevity startups

January 17, 2025

Farewell to the $200 million woolly mammoth and TikTok

January 17, 2025

Nord Security founder launches Nexos.ai to help enterprises move AI projects from pilot to production

January 17, 2025

Data proves it remains difficult for startups to raise capital, even though VCs invested $75 billion in the fourth quarter

January 16, 2025

Apple suspends AI notification summaries for news after generating false alerts

January 16, 2025

Nvidia releases more tools and guardrails to help enterprises adopt AI agents

January 16, 2025

Leave A Reply Cancel Reply

Top Reviews
Editors Picks

7 days left: Founders and VCs save over $300 on all stage passes

March 24, 2025

AI chip startup Furiosaai reportedly rejecting $800 million acquisition offer from Meta

March 24, 2025

20 Hottest Open Source Startups of 2024

March 22, 2025

Andrill may build a weapons factory in the UK

March 21, 2025
About Us
About Us

Welcome to Tech Brunch, your go-to destination for cutting-edge insights, news, and analysis in the fields of Artificial Intelligence (AI), Cryptocurrency, Technology, and Startups. At Tech Brunch, we are passionate about exploring the latest trends, innovations, and developments shaping the future of these dynamic industries.

Our Picks

Google suggests opening a play store for more real money games in India

July 30, 2025

Palo Alto Networks agrees to buy Cyberark for $25 billion

July 30, 2025

Germ brings end-to-end encrypted messages to BlueSky

July 30, 2025

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

© 2025 TechBrunch. Designed by TechBrunch.
  • Home
  • About Tech Brunch
  • Advertise with Tech Brunch
  • Contact us
  • DMCA Notice
  • Privacy Policy
  • Terms of Use

Type above and press Enter to search. Press Esc to cancel.